Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats
Thermal comfort is associated with clothing insulation, conveying a level of satisfaction with the thermal surroundings. Besides, clothing insulation is commonly associated with indoor thermal comfort. However, clothing classification in smart homes might save energy when the end-user wears appropri...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/5/1811 |
| _version_ | 1797475227783921664 |
|---|---|
| author | Adán Medina Juana Isabel Méndez Pedro Ponce Therese Peffer Alan Meier Arturo Molina |
| author_facet | Adán Medina Juana Isabel Méndez Pedro Ponce Therese Peffer Alan Meier Arturo Molina |
| author_sort | Adán Medina |
| collection | DOAJ |
| description | Thermal comfort is associated with clothing insulation, conveying a level of satisfaction with the thermal surroundings. Besides, clothing insulation is commonly associated with indoor thermal comfort. However, clothing classification in smart homes might save energy when the end-user wears appropriate clothes to save energy and obtain thermal comfort. Furthermore, object detection and classification through Convolutional Neural Networks has increased over the last decade. There are real-time clothing garment classifiers, but these are oriented towards single garment recognition for texture, fabric, shape, or style. Consequently, this paper proposes a CNN model classification for the implementation of these classifiers on cameras. First, the Fashion MNIST was analyzed and compared with the VGG16, Inceptionvv4, TinyYOLOv3, and ResNet18 classification algorithms to determine the best clo classifier. Then, for real-time analysis, a new dataset with 12,000 images was created and analyzed with the YOLOv3 and TinyYOLO. Finally, an Azure Kinect DT was employed to analyze the clo value in real-time. Moreover, real-time analysis can be employed with any other webcam. The model recognizes at least three garments of a clothing ensemble, proving that it identifies more than a single clothing garment. Besides, the model has at least 90% accuracy in the test dataset, ensuring that it can be generalized and is not overfitting. |
| first_indexed | 2024-03-09T20:41:10Z |
| format | Article |
| id | doaj.art-cc433eae7292460992186aa3f1faddcf |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T20:41:10Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-cc433eae7292460992186aa3f1faddcf2023-11-23T22:57:50ZengMDPI AGEnergies1996-10732022-03-01155181110.3390/en15051811Using Deep Learning in Real-Time for Clothing Classification with Connected ThermostatsAdán Medina0Juana Isabel Méndez1Pedro Ponce2Therese Peffer3Alan Meier4Arturo Molina5School of Engineering and Sciences, Tecnologico de Monterrey, Mexico City 14380, MexicoSchool of Engineering and Sciences, Tecnologico de Monterrey, Mexico City 14380, MexicoSchool of Engineering and Sciences, Tecnologico de Monterrey, Mexico City 14380, MexicoInstitute for Energy and Environment, University of California, Berkeley, CA 94720, USAEnergy and Efficiency Institute, University of California, Davis, CA 95616, USASchool of Engineering and Sciences, Tecnologico de Monterrey, Mexico City 14380, MexicoThermal comfort is associated with clothing insulation, conveying a level of satisfaction with the thermal surroundings. Besides, clothing insulation is commonly associated with indoor thermal comfort. However, clothing classification in smart homes might save energy when the end-user wears appropriate clothes to save energy and obtain thermal comfort. Furthermore, object detection and classification through Convolutional Neural Networks has increased over the last decade. There are real-time clothing garment classifiers, but these are oriented towards single garment recognition for texture, fabric, shape, or style. Consequently, this paper proposes a CNN model classification for the implementation of these classifiers on cameras. First, the Fashion MNIST was analyzed and compared with the VGG16, Inceptionvv4, TinyYOLOv3, and ResNet18 classification algorithms to determine the best clo classifier. Then, for real-time analysis, a new dataset with 12,000 images was created and analyzed with the YOLOv3 and TinyYOLO. Finally, an Azure Kinect DT was employed to analyze the clo value in real-time. Moreover, real-time analysis can be employed with any other webcam. The model recognizes at least three garments of a clothing ensemble, proving that it identifies more than a single clothing garment. Besides, the model has at least 90% accuracy in the test dataset, ensuring that it can be generalized and is not overfitting.https://www.mdpi.com/1996-1073/15/5/1811clothing classifierCNN modelsthermal comfortconnected thermostat |
| spellingShingle | Adán Medina Juana Isabel Méndez Pedro Ponce Therese Peffer Alan Meier Arturo Molina Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats Energies clothing classifier CNN models thermal comfort connected thermostat |
| title | Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats |
| title_full | Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats |
| title_fullStr | Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats |
| title_full_unstemmed | Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats |
| title_short | Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats |
| title_sort | using deep learning in real time for clothing classification with connected thermostats |
| topic | clothing classifier CNN models thermal comfort connected thermostat |
| url | https://www.mdpi.com/1996-1073/15/5/1811 |
| work_keys_str_mv | AT adanmedina usingdeeplearninginrealtimeforclothingclassificationwithconnectedthermostats AT juanaisabelmendez usingdeeplearninginrealtimeforclothingclassificationwithconnectedthermostats AT pedroponce usingdeeplearninginrealtimeforclothingclassificationwithconnectedthermostats AT theresepeffer usingdeeplearninginrealtimeforclothingclassificationwithconnectedthermostats AT alanmeier usingdeeplearninginrealtimeforclothingclassificationwithconnectedthermostats AT arturomolina usingdeeplearninginrealtimeforclothingclassificationwithconnectedthermostats |